Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region
Groundwater is essential for sustaining human life and ecosystems as a freshwater resource. However, intensive groundwater pumping (GWP) can deplete groundwater levels, and exacerbate issues such as sea-level rise and saltwater intrusion in coastal areas, further affecting the availability and acces...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-12-01
|
| Series: | Frontiers in Water |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frwa.2024.1509945/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846118139742388224 |
|---|---|
| author | Jamie Kim Yueling Ma Yueling Ma Reed M. Maxwell Reed M. Maxwell Reed M. Maxwell |
| author_facet | Jamie Kim Yueling Ma Yueling Ma Reed M. Maxwell Reed M. Maxwell Reed M. Maxwell |
| author_sort | Jamie Kim |
| collection | DOAJ |
| description | Groundwater is essential for sustaining human life and ecosystems as a freshwater resource. However, intensive groundwater pumping (GWP) can deplete groundwater levels, and exacerbate issues such as sea-level rise and saltwater intrusion in coastal areas, further affecting the availability and accessibility of groundwater. To address these challenges, accurate monitoring and modeling of water table depth (WTD), a key indicator of groundwater storage, is useful for sustainable groundwater management. This work studies the implementation of a regression-enhanced random forest (RERF) model to predict WTD anomalies with pumping as a major input for New Jersey, a coastal state in the United States. The predicted WTD anomalies align well with observations, with a test Nash-Sutcliffe Efficiency (NSE) of 0.49, a test Pearson correlation coefficient (r) of 0.72, and a test root-squared mean error (RMSE) of 1.61 m. Based on a permutation feature importance, the most important input variables in the model for predicting WTD anomalies were long-term mean WTD, precipitation minus evapotranspiration (PME), and GWP. Using the trained RERF model, we generated 90 m spatial resolution WTD anomaly maps for New Jersey for January and July 2015, showing areas of increasing and decreasing WTD. We then inverted the RERF model to predict GWP using WTD anomalies, land cover, and a cross metric as additional inputs. This approach was less effective, yielding a test NSE of 0.40, a test r of 0.65, and a test RMSE of 15.44 million liters/month. A permutation feature importance revealed the most important input variables to be PME, long-term mean WTD, and topographic slope. Again we generated 90 m GWP maps for New Jersey for January and July 2015, offering finer resolution than the previous maps at the subwatershed level. Focusing on New Jersey, the study provides insights into the relationship between WTD anomalies and its critical input variables including GWP in coastal areas. Moreover, significant gaps in WTD observations persist in New Jersey, highlighting the need for comprehensive monitoring efforts. Thus, by employing ML techniques and leveraging available data, this study contributes to improving groundwater management practices and informing future decision-making. |
| format | Article |
| id | doaj-art-991394b13d8041769b10eebfbd5dc970 |
| institution | Kabale University |
| issn | 2624-9375 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Water |
| spelling | doaj-art-991394b13d8041769b10eebfbd5dc9702024-12-18T06:43:38ZengFrontiers Media S.A.Frontiers in Water2624-93752024-12-01610.3389/frwa.2024.15099451509945Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal regionJamie Kim0Yueling Ma1Yueling Ma2Reed M. Maxwell3Reed M. Maxwell4Reed M. Maxwell5Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ, United StatesHigh Meadows Environmental Institute, Princeton University, Princeton, NJ, United StatesIntegrated GroundWater Modeling Center, Princeton University, Princeton, NJ, United StatesDepartment of Civil and Environmental Engineering, Princeton University, Princeton, NJ, United StatesHigh Meadows Environmental Institute, Princeton University, Princeton, NJ, United StatesIntegrated GroundWater Modeling Center, Princeton University, Princeton, NJ, United StatesGroundwater is essential for sustaining human life and ecosystems as a freshwater resource. However, intensive groundwater pumping (GWP) can deplete groundwater levels, and exacerbate issues such as sea-level rise and saltwater intrusion in coastal areas, further affecting the availability and accessibility of groundwater. To address these challenges, accurate monitoring and modeling of water table depth (WTD), a key indicator of groundwater storage, is useful for sustainable groundwater management. This work studies the implementation of a regression-enhanced random forest (RERF) model to predict WTD anomalies with pumping as a major input for New Jersey, a coastal state in the United States. The predicted WTD anomalies align well with observations, with a test Nash-Sutcliffe Efficiency (NSE) of 0.49, a test Pearson correlation coefficient (r) of 0.72, and a test root-squared mean error (RMSE) of 1.61 m. Based on a permutation feature importance, the most important input variables in the model for predicting WTD anomalies were long-term mean WTD, precipitation minus evapotranspiration (PME), and GWP. Using the trained RERF model, we generated 90 m spatial resolution WTD anomaly maps for New Jersey for January and July 2015, showing areas of increasing and decreasing WTD. We then inverted the RERF model to predict GWP using WTD anomalies, land cover, and a cross metric as additional inputs. This approach was less effective, yielding a test NSE of 0.40, a test r of 0.65, and a test RMSE of 15.44 million liters/month. A permutation feature importance revealed the most important input variables to be PME, long-term mean WTD, and topographic slope. Again we generated 90 m GWP maps for New Jersey for January and July 2015, offering finer resolution than the previous maps at the subwatershed level. Focusing on New Jersey, the study provides insights into the relationship between WTD anomalies and its critical input variables including GWP in coastal areas. Moreover, significant gaps in WTD observations persist in New Jersey, highlighting the need for comprehensive monitoring efforts. Thus, by employing ML techniques and leveraging available data, this study contributes to improving groundwater management practices and informing future decision-making.https://www.frontiersin.org/articles/10.3389/frwa.2024.1509945/fullgroundwater levelwater table depthgroundwater pumpingmachine learningregression-enhanced random forest modelgroundwater monitoring and management |
| spellingShingle | Jamie Kim Yueling Ma Yueling Ma Reed M. Maxwell Reed M. Maxwell Reed M. Maxwell Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region Frontiers in Water groundwater level water table depth groundwater pumping machine learning regression-enhanced random forest model groundwater monitoring and management |
| title | Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| title_full | Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| title_fullStr | Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| title_full_unstemmed | Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| title_short | Integrating groundwater pumping data with regression-enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| title_sort | integrating groundwater pumping data with regression enhanced random forest models to improve groundwater monitoring and management in a coastal region |
| topic | groundwater level water table depth groundwater pumping machine learning regression-enhanced random forest model groundwater monitoring and management |
| url | https://www.frontiersin.org/articles/10.3389/frwa.2024.1509945/full |
| work_keys_str_mv | AT jamiekim integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion AT yuelingma integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion AT yuelingma integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion AT reedmmaxwell integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion AT reedmmaxwell integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion AT reedmmaxwell integratinggroundwaterpumpingdatawithregressionenhancedrandomforestmodelstoimprovegroundwatermonitoringandmanagementinacoastalregion |